def _skip_if_none_of(module_names):
if isinstance(module_names, string_types):
_skip_if_no(module_names)
if module_names == 'bs4':
import bs4
if bs4.__version__ == LooseVersion('4.2.0'):
raise nose.SkipTest("Bad version of bs4: 4.2.0")
else:
not_found = [module_name for module_name in module_names if not
_have_module(module_name)]
if set(not_found) & set(module_names):
raise nose.SkipTest("{0!r} not found".format(not_found))
if 'bs4' in module_names:
import bs4
if bs4.__version__ == LooseVersion('4.2.0'):
raise nose.SkipTest("Bad version of bs4: 4.2.0")
python类__version__()的实例源码
test_html.py 文件源码
项目：PyDataLondon29-EmbarrassinglyParallelDAWithAWSLambda
作者: SignalMedia
项目源码
文件源码
阅读 26
收藏 0
点赞 0
评论 0
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
test_html.py 文件源码
项目：PyDataLondon29-EmbarrassinglyParallelDAWithAWSLambda
作者: SignalMedia
项目源码
文件源码
阅读 27
收藏 0
点赞 0
评论 0
def test_bs4_version_fails():
_skip_if_none_of(('bs4', 'html5lib'))
import bs4
if bs4.__version__ == LooseVersion('4.2.0'):
tm.assert_raises(AssertionError, read_html, os.path.join(DATA_PATH,
"spam.html"),
flavor='bs4')
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print("Diagnostic running on Beautiful Soup %s" % __version__)
print("Python version %s" % sys.version)
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
except ImportError as e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print("Found html5lib version %s" % html5lib.__version__)
except ImportError as e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print('"%s" looks like a filename. Reading data from the file.' % data)
with open(data) as fp:
data = fp.read()
elif data.startswith("http:") or data.startswith("https:"):
print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print()
for parser in basic_parsers:
print("Trying to parse your markup with %s" % parser)
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("Here's what %s did with the markup:" % parser)
print(soup.prettify())
print("-" * 80)
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print("Diagnostic running on Beautiful Soup %s" % __version__)
print("Python version %s" % sys.version)
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
except ImportError as e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print("Found html5lib version %s" % html5lib.__version__)
except ImportError as e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print('"%s" looks like a filename. Reading data from the file.' % data)
with open(data) as fp:
data = fp.read()
elif data.startswith("http:") or data.startswith("https:"):
print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print()
for parser in basic_parsers:
print("Trying to parse your markup with %s" % parser)
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("Here's what %s did with the markup:" % parser)
print(soup.prettify())
print("-" * 80)
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print("Diagnostic running on Beautiful Soup %s" % __version__)
print("Python version %s" % sys.version)
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
except ImportError as e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print("Found html5lib version %s" % html5lib.__version__)
except ImportError as e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print('"%s" looks like a filename. Reading data from the file.' % data)
with open(data) as fp:
data = fp.read()
elif data.startswith("http:") or data.startswith("https:"):
print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print()
for parser in basic_parsers:
print("Trying to parse your markup with %s" % parser)
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("Here's what %s did with the markup:" % parser)
print(soup.prettify())
print("-" * 80)
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print("Diagnostic running on Beautiful Soup %s" % __version__)
print("Python version %s" % sys.version)
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
except ImportError as e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print("Found html5lib version %s" % html5lib.__version__)
except ImportError as e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print('"%s" looks like a filename. Reading data from the file.' % data)
with open(data) as fp:
data = fp.read()
elif data.startswith("http:") or data.startswith("https:"):
print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print()
for parser in basic_parsers:
print("Trying to parse your markup with %s" % parser)
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("Here's what %s did with the markup:" % parser)
print(soup.prettify())
print("-" * 80)
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print("Diagnostic running on Beautiful Soup %s" % __version__)
print("Python version %s" % sys.version)
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
except ImportError as e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print("Found html5lib version %s" % html5lib.__version__)
except ImportError as e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print('"%s" looks like a filename. Reading data from the file.' % data)
with open(data) as fp:
data = fp.read()
elif data.startswith("http:") or data.startswith("https:"):
print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print()
for parser in basic_parsers:
print("Trying to parse your markup with %s" % parser)
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("Here's what %s did with the markup:" % parser)
print(soup.prettify())
print("-" * 80)
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print("Diagnostic running on Beautiful Soup %s" % __version__)
print("Python version %s" % sys.version)
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
except ImportError as e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print("Found html5lib version %s" % html5lib.__version__)
except ImportError as e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print('"%s" looks like a filename. Reading data from the file.' % data)
data = open(data).read()
elif data.startswith("http:") or data.startswith("https:"):
print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print()
for parser in basic_parsers:
print("Trying to parse your markup with %s" % parser)
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("Here's what %s did with the markup:" % parser)
print(soup.prettify())
print("-" * 80)
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print("Diagnostic running on Beautiful Soup %s" % __version__)
print("Python version %s" % sys.version)
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
except ImportError as e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print("Found html5lib version %s" % html5lib.__version__)
except ImportError as e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print('"%s" looks like a filename. Reading data from the file.' % data)
with open(data) as fp:
data = fp.read()
elif data.startswith("http:") or data.startswith("https:"):
print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print()
for parser in basic_parsers:
print("Trying to parse your markup with %s" % parser)
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("Here's what %s did with the markup:" % parser)
print(soup.prettify())
print("-" * 80)
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print("Diagnostic running on Beautiful Soup %s" % __version__)
print("Python version %s" % sys.version)
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
except ImportError as e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print("Found html5lib version %s" % html5lib.__version__)
except ImportError as e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print('"%s" looks like a filename. Reading data from the file.' % data)
with open(data) as fp:
data = fp.read()
elif data.startswith("http:") or data.startswith("https:"):
print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print()
for parser in basic_parsers:
print("Trying to parse your markup with %s" % parser)
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("Here's what %s did with the markup:" % parser)
print(soup.prettify())
print("-" * 80)
html.py 文件源码
项目：PyDataLondon29-EmbarrassinglyParallelDAWithAWSLambda
作者: SignalMedia
项目源码
文件源码
阅读 32
收藏 0
点赞 0
评论 0
def _parser_dispatch(flavor):
"""Choose the parser based on the input flavor.
Parameters
----------
flavor : str
The type of parser to use. This must be a valid backend.
Returns
-------
cls : _HtmlFrameParser subclass
The parser class based on the requested input flavor.
Raises
------
ValueError
* If `flavor` is not a valid backend.
ImportError
* If you do not have the requested `flavor`
"""
valid_parsers = list(_valid_parsers.keys())
if flavor not in valid_parsers:
raise ValueError('%r is not a valid flavor, valid flavors are %s' %
(flavor, valid_parsers))
if flavor in ('bs4', 'html5lib'):
if not _HAS_HTML5LIB:
raise ImportError("html5lib not found, please install it")
if not _HAS_BS4:
raise ImportError(
"BeautifulSoup4 (bs4) not found, please install it")
import bs4
if bs4.__version__ == LooseVersion('4.2.0'):
raise ValueError("You're using a version"
" of BeautifulSoup4 (4.2.0) that has been"
" known to cause problems on certain"
" operating systems such as Debian. "
"Please install a version of"
" BeautifulSoup4 != 4.2.0, both earlier"
" and later releases will work.")
else:
if not _HAS_LXML:
raise ImportError("lxml not found, please install it")
return _valid_parsers[flavor]
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print("Diagnostic running on Beautiful Soup %s" % __version__)
print("Python version %s" % sys.version)
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
except ImportError as e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print("Found html5lib version %s" % html5lib.__version__)
except ImportError as e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print('"%s" looks like a filename. Reading data from the file.' % data)
with open(data) as fp:
data = fp.read()
elif data.startswith("http:") or data.startswith("https:"):
print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print()
for parser in basic_parsers:
print("Trying to parse your markup with %s" % parser)
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("Here's what %s did with the markup:" % parser)
print(soup.prettify())
print("-" * 80)
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print("Diagnostic running on Beautiful Soup %s" % __version__)
print("Python version %s" % sys.version)
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
except ImportError as e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print("Found html5lib version %s" % html5lib.__version__)
except ImportError as e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print('"%s" looks like a filename. Reading data from the file.' % data)
with open(data) as fp:
data = fp.read()
elif data.startswith("http:") or data.startswith("https:"):
print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print()
for parser in basic_parsers:
print("Trying to parse your markup with %s" % parser)
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("Here's what %s did with the markup:" % parser)
print(soup.prettify())
print("-" * 80)
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print("Diagnostic running on Beautiful Soup %s" % __version__)
print("Python version %s" % sys.version)
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
except ImportError as e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print("Found html5lib version %s" % html5lib.__version__)
except ImportError as e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print('"%s" looks like a filename. Reading data from the file.' % data)
with open(data) as fp:
data = fp.read()
elif data.startswith("http:") or data.startswith("https:"):
print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print()
for parser in basic_parsers:
print("Trying to parse your markup with %s" % parser)
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print("Here's what %s did with the markup:" % parser)
print(soup.prettify())
print("-" * 80)
